Face-Name Tracking Analysing System By Cluster Using Constrain K-Means
Auto face identification of characters in films has drawn most research interests and led to many interesting applications. Since huge variation in the appearance of each character is found, it is a challenging problem. Existing methods evaluates promising results in clean environment, the performances are limited in complex movie scenes due to the noises generated during the face tracking and face clustering process. This study presents two schemes of global face-name matching based framework for robust character identification. The contributions of this study include: A noise insensitive character relationship representation is incorporated. The study introduces an edit operation based graph matching algorithm. Complex character changes are handled by simultaneously graph partition and graph matching. Beyond existing character identification approaches, we further perform an in-depth sensitivity analysis by introducing two types of simulated noises. The proposed schemes demonstrate state-of-the-art performance on movie character identification in various movies. The project has been developed using Visual Studio .Net 2005 as front end and SQL Server 2000 as back end. C# is used the coding language.